Stars
Make your models invariant to changes in scale.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
SALMONN: Speech Audio Language Music Open Neural Network
[JBHI] SCKansformer: Fine-Grained Classification of Bone Marrow Cells via Kansformer Backbone and Hierarchical Attention Mechanisms
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
🕹️SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy
基于Flask开发后端、VUE开发前端框架，在WEB端部署YOLOv5目标检测模型
Stream video of pedestrians detection using opencv background subtraction and python Flask microframework
This repository includes Endoscopic colorectal polyp detection based on improved YOLOv8. We employ deformable Conv V2 and EMA modules to improve the YOLOv8 model, further achieving a significant pe…
An open dataset for object detection in remote sensing images
Official code of the paper "Anchor pruning for object detection"
pruning for OpenMMLab Detection Toolbox
Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism
[CVPR 2023] Official implementation of the paper "Semi-DETR: Semi-Supervised Object Detection with Detection Transformers"
An official implementation of CVPR 2022 paper "Label Matching Semi-Supervised Object Detection".
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
🕶 A curated list of Tiny Object Detection papers and related resources.
Semantic segmentation of high-resolution remote sensing images
A lightweight script for performing Kalman filter based object tracking using MMDetection models.
Using faster RCNN with the backbone Resnet Strikes Back in MMDetection to implement an IOU-based tracker with Kalman Filter and delayed deletion.
pytorch implementation of basic kmeans algorithm(lloyd method with forgy initialization) with gpu support
Official implementation of the CVPR23 paper: Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection
Lightweight Python library for adding real-time multi-object tracking to any detector.
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.